Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing side effects: 'New revision, effect report', whole-model scope for origin ('every one in the world'), creation of an IfcProjectedCRS when the file has no map conversion, and the all-or-nothing plan semantics. 'A call that succeeds is not a job that's done' hints at asynchronous completion but is too cryptic to be actionable. Nothing contradicts readOnlyHint=false, idempotentHint=true, or destructiveHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Every clause carries information and the purpose leads, but the prose is telegraphic to the point of strain: dropped articles, semicolon-chained conditionals, and a closing line ('A call that succeeds is not a job that's done') that reads as aphorism rather than instruction. Density is high; parseability on first read is not.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, nested-object mutation tool with no output schema, the description covers the mode semantics, the dry_run/plan_id lifecycle, revision creation, and conflict codes (PLAN_REQUIRED, PLAN_CHANGED). Gaps are minor: the effect report's shape is not characterized, and true_north_deg's relationship to the origin mode is not stated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is 3, and the description earns above that by adding cross-parameter conditions the schema cannot express: georeference only creates an IfcMapConversion when epsg, eastings, northings and orthogonal_height are all named, and it works 'in the map unit of its CRS'. It also ties plan_id back to the PLAN_REQUIRED/dry_run output. true_north_deg and expect_beyond get only glancing coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource and then enumerates the four distinct modes (origin, TrueNorth, georeference, site) with what each one actually touches: 'origin moves elements, every one in the world', 'georeference changes the one IfcMapConversion', 'site sets RefLatitude/RefLongitude ... of one IfcSite'. That is far more than a restatement of the name. It stops short of naming a sibling tool to describe against (e.g. move_elements), so mode switching is clear but tool selection is left partly to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The plan workflow is spelled out: 'PLAN_REQUIRED gives the plan_id to run', and plan_id 'Execute exactly the plan a dry_run returned, all or nothing'. It also sets ordering constraints for clone plans ('plan the second after the first ran, else PLAN_CHANGED'). What is missing is explicit when-not guidance, e.g. when to use this instead of move_elements for repositioning geometry.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.